• 한국경영정보학회:학술대회논문집
• /
• 2007.06a
• /
• pp.608-613
• /
• 2007

Prediction of corporate bankruptcies has long been an important topic and has been studied extensively in the finance and management literature because it is an essential basis for the risk management of financial institutions. Recently, support vector machines (SVMs) are becoming popular as a tool for bankruptcy prediction because they use a risk function consisting of the empirical error and a regularized term which is derived from the structural risk minimization principle. In addition, they don't require huge training samples and have little possibility of overfitting. However. in order to Use SVM, a user should determine several factors such as the parameters ofa kernel function, appropriate feature subset, and proper instance subset by heuristics, which hinders accurate prediction results when using SVM In this study, we propose a novel hybrid SVM classifier with simultaneous optimization of feature subsets, instance subsets, and kernel parameters. This study introduces genetic algorithms (GAs) to optimize the feature selection, instance selection, and kernel parameters simultaneously. Our study applies the proposed model to the real-world case for bankruptcy prediction. Experimental results show that the prediction accuracy of conventional SVM may be improved significantly by using our model.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.331-336
• /
• 2005

A lot of manufacturing knowledge and method have applied to increase manufacturing efficiency in industry field. DES(Discrete Event Simulation) is one of solution to deal with manufacturing problems in factory. Beginning of research, old maintenance system of KNR ( Korea National Railroad) and its technical problems are basically investigated. KNR has maintained railway vehicle with their own solution based on experience. Very advanced railway vehicles such as KTX (Korea Train Express) and TTX(Tilting Train Express) will be difficult to maintain with their old maintenance method. In order to apply knowledge of DES, maintenance field of railway must be considered. Imaginary maintenance machine are selected to variable of DES. Maintenance capability of each machine will be evaluated base on imaginary data from imaginary machine. The machine could be very expensive as well as difficult to replace. Target of research is minimization of number of machine in railway workshop. So basic knowledge of discrete event simulation is introduced. Then five essential stages of discrete event simulation are provided. Each maintenance case defined as event. Each event is discrete and simulated base on different case such as one maintenance line with one machine and one maintenance line with two machines in railway workshop. simple maintenance method, discrete event simulation, will be come out very powerful in complicate maintenance system and will be helpful to reduce maintenance cost as well as maintenance labor.

• The KSFM Journal of Fluid Machinery
• /
• v.3 no.4 s.9
• /
• pp.30-37
• /
• 2000

Several reverse design methods are developed and applied to the suction or pressure surface for finding design values of blade geometry for a given axial turbine blade. Re-designed blade profiles using shape parameters are compared with measured blade data. Essential shape parameters for blade design are induced by the procedure of reverse design for best fitting. Characteristics of shape parameters are evaluated through the system design method and restriction conditions of structural stability or aerodynamic flow loss. Some of shape parameters i.e blade radius or exit blade angle etc., are classified to weakly adjustable shape parameters, otherwise strongly adjustable shape parameters which would be applied for controlling blade shape. Average deviation values between the measured data and re-designed blade using shape parameters are calculated for each design method. Comparing with the average deviation for a given blade geometry, minimum shape parameters required to design a blade geometry are obtained.

• Journal of Institute of Control, Robotics and Systems
• /
• v.1 no.2
• /
• pp.112-118
• /
• 1995

In designing assembly lines, it is required that the lines should not only meet the demand of the product, but also minimize the assembly cost associated with the line. For such a purpose, numerous research efforts have been made on either the assembly sequence generation or the assembly line balancing. However, the works dealing with both the research problems have been seldom reported in literature. When assembly sequences are generated without consideration of line balancing, additional cost may be incurred, because the sequences may not guarantee the minimum number of workstations. Therefore, it is essential to consider line balancing in the generation of cost-effective assembly sequences. To incorporate the two research problems into one, this paper treats a single-model and deterministic (SMD) assembly line balancing (ALB) problem, and proposes a new method for generating line-balanced robotic assembly sequences by using a simulated annealing. In this method, an energy function is derived in consideration of the satisfaction of assembly constraints, and the minimization of both the assembly cost and the idle time. Then, the energy function is iteratively minimized and occasionally perturbed by the simulated annealing. When no further change in energy occurs, an assembly sequence with consideration of line balancing is finally found. To show the effectiveness of the proposed scheme, a case study for an electrical relay is presented.

• Proceedings of the IEEK Conference
• /
• 2001.10a
• /
• pp.80-83
• /
• 2001

According to the EPA in Taiwan report, 9.05 million metric tons of solid wastes were generated in 1999, and the waste glass was accounted of 4.95 percent. However, with the increasing tonnage of disposal cost and existing disposal sites are reaching full capacity, recycling is currently accepted as a sustainable approach to waste management. Therefore, it's essential and urgent that the government in Taiwan establish the recycling and recovery framework for the minimization of the solid waste, reduction of materials and energy consumption, and the encouragement for the reuse, recycle and recovery development. To achieve this Boal, Taiwan has been strived for a long period of time in waste glass recovery and recycle. Waste glass, unlike other kinds of resource waste, is 100% recyclable. The EPA in Taiwan now center on a lot of different kinds of waste glass, such as glass container, flat glass, CRT glass, windshields glass, fluorescent lamps, and waste pesticide glass container. This article will focus on the framework of the recycling market access, and also try to provide some strategies to improve waste glass recycling efficiently.

• Korean Institute of Interior Design Journal
• /
• v.24 no.2
• /
• pp.67-77
• /
• 2015

This study is to contemplate an ultimate goal and new methodology the architecture and space design community should pursue forward by analyzing concepts in Kengo Kuma's idea of "Anti-object" and examining his design methods and characteristics. To this end, I reviewed space design methods and features in his book of "Anti-Object" and his architectures built around in 2000. The result is as in the followings. (1) Contact is an essential concept of "Anti-object" to connect and integrate divided materials and consciousness with time and space. (2) Elimination is a meaningful way to reverse "cohesiveness" of agglomerated cluster which is a form of object and reconstruct it into the form of passive and acceptive "Anti-object". This idea is realized through overlap of material property and removal of massing. (3) Minimization is a concept of "Anti-object" to set the temporality free from constraints of materials. Three-dimensional transparent faces and lines or patterns of porous materials can be used to remove static and coercive volume. (4) A particle is a "reflector of its environment." It rebuilds one-way or disconnected communication between human and architecture into an interactive one. Kengo Kuma materializes this "particle" by exploring positional relation with physical paths, precise details and measurements.

• Journal of Animal Environmental Science
• /
• v.1 no.1
• /
• pp.83-102
• /
• 1995

Composting is an ecologically sound method of recycling organic waste. Its advantages include the maintenance of soil fertility and improvement of soil physicochemical property. It is an essential part of the waste minimization. That is, composting should be included to increase the recycling rate up to more than 20%. To encourage composting of waste, it is necessary to develop some effective composters of small scale facilities and densely populated areas. For medium and large-size facilities, the optimum process should be selected. Technical counselling and support is desirable for small scale composters for urban residential and rural area. On the other hand, adequate amendment of relevant legislation should be followed to encourage composting. An example of unreasonable legislation is the current fertilizer management act. According to the regulation, the maximum allowable limit of lead in the compost is less than 150ppm, which is too strict. This limit should be increased to at least 300ppm, which is the observed level in most states in USA. At the same time, sound infrastructure should be established and decent publicity work should be achieved to accelerate composting activity. In this paper the desirable standard for some heavy metal concentration in the compost were suggested.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.4A
• /
• pp.337-344
• /
• 2011

In this paper, a multiple-input and multiple-output (MIMO) spatial multiplexing (SM) relay system is studied in a bit error rate (BER) sense, where every node is deployed with multiple antennas. In order to efficiently use the limited power resource, it is essential to optimally allocate the power to nodes and antennas. In this context, the power allocation (PA) algorithm based on minimum BER (MBER) for a MIMO SM relay system is proposed, which is derived by direct minimization of the average BER, and divided into inter-node and inter-antenna PA algorithm. The proposed scheme outperforms the conventional equal power allocation (EPA) algorithm without extra power consumption.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.2
• /
• pp.279-284
• /
• 2009

In swarm robot systems, each robot must behaves by itself according to the its states and environments, and if necessary, must cooperates with other robots in order to carry out a given task. Therefore it is essential that each robot has both learning and evolution ability to adapt the dynamic environments. In this paper, reinforcement learning method using many SVM based on structural risk minimization and distributed genetic algorithms is proposed for behavior learning and evolution of collective autonomous mobile robots. By distributed genetic algorithm exchanging the chromosome acquired under different environments by communication each robot can improve its behavior ability. Specially, in order to improve the performance of evolution, selective crossover using the characteristic of reinforcement learning that basis of Cascade SVM is adopted in this paper.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.854-857
• /
• 2015

As the number of devices integrated on system-on-chip(SoC) increases exponentially, energy reduction technology is essential. Dynamic Voltage and Frequency Scaling (DVFS) is a very effective technique for reducing power consumption. Since it requires complex voltage regulators and PLL circuits, DVFS tends to have significant overheads. In this paper, we propose a new voltage selection algorithm to minimize transition overhead for multiprocessor SoC (MPSoC). Simulation results show that proposed algorithm appears less energy consumption with transition overhead even though maintains performance.